Base44 Superagents-AI agent that does it all
Mini toolsVoxCPM 1.5
By OpenBMB
VoxCPM1.5 is the latest VoxCPM tokenizer-free text-to-speech model from OpenBMB and ModelBest. It directly produces continuous speech representations from text for expressive, context-aware synthesis and highly realistic zero-shot voice cloning in Chinese and English. The 800M-parameter model supports 44.1 kHz audio, low real-time factors for streaming, and Apache-2.0 licensed weights with both full and LoRA fine-tuning to build custom voices.
New
Audio
Gen 4
Overview
VoxCPM1.5 is OpenBMB’s tokenizer-free TTS model that generates expressive, context-aware speech and realistic zero-shot voice clones in Chinese and English, with real-time streaming and open-source weights that support full and LoRA fine-tuning.
About OpenBMB
OpenBMB is short for Open Lab for Big Model Base. The goal of OpenBMB is to build the model base and toolkit for large-scale pre-trained language models.
Website:
openbmb.cn
Tools using VoxCPM 1.5
No tools found for this model yet.
Last updated: February 25, 2026
